POWER9 introduces a new mode for the decrementer register, called
large decrementer mode, in which the decrementer counter is 56 bits
wide rather than 32, and reads sign-extend rather than zero-extending.
Since KVM code reads and writes the host decrementer value in a few
places, it needs to be aware of the need to treat the decrementer
value as a 64-bit quantity, and only do a 32-bit sign extension when
large decrementer mode is not in effect. To enable the sign extension
to be removed in large decrementer mode, we use a CPU feature bit to
indicate that large decrementer mode is in effect. This CPU feature
bit is derived from the ibm,pa-features property in the firmware
device tree. This bit is already set by firmware in the device tree
that the kernel uses when running as a host. We change the kernel
timer code to use this bit and enable large decrementer mode whenever
it is set (even if firmware tells us that the large decrementer mode
only gives us 32 bits) so that we get the sign extension in hardware.
For now, the guest still uses the decrementer in small decrementer
(32-bit) mode.
This is partly based on an earlier patch by Oliver O'Halloran.
Cc: stable@xxxxxxxxxxxxxxx # v4.10+
Signed-off-by: Paul Mackerras <paulus@xxxxxxxxxx>
---
arch/powerpc/include/asm/cputable.h | 4 +++-
arch/powerpc/kernel/prom.c | 1 +
arch/powerpc/kernel/time.c | 7 ++-----
arch/powerpc/kvm/book3s_hv_interrupts.S | 2 ++
arch/powerpc/kvm/book3s_hv_rmhandlers.S | 23 +++++++++++++++++------
5 files changed, 25 insertions(+), 12 deletions(-)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index c2d5095..99c3c56 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -216,6 +216,7 @@ enum {
#define CPU_FTR_PMAO_BUG LONG_ASM_CONST(0x1000000000000000)
#define CPU_FTR_SUBCORE LONG_ASM_CONST(0x2000000000000000)
#define CPU_FTR_POWER9_DD1 LONG_ASM_CONST(0x4000000000000000)
+#define CPU_FTR_LARGE_DEC LONG_ASM_CONST(0x8000000000000000)
#ifndef __ASSEMBLY__
@@ -496,7 +497,8 @@ enum {
(CPU_FTRS_POWER4 | CPU_FTRS_PPC970 | CPU_FTRS_POWER5 | \
CPU_FTRS_POWER6 | CPU_FTRS_POWER7 | CPU_FTRS_POWER8E | \
CPU_FTRS_POWER8 | CPU_FTRS_POWER8_DD1 | CPU_FTRS_CELL | \
- CPU_FTRS_PA6T | CPU_FTR_VSX | CPU_FTRS_POWER9 | CPU_FTRS_POWER9_DD1)
+ CPU_FTRS_PA6T | CPU_FTR_VSX | CPU_FTRS_POWER9 | \
+ CPU_FTRS_POWER9_DD1 | CPU_FTR_LARGE_DEC)
#endif
#else
enum {
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 40c4887..b315dff 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -165,6 +165,7 @@ static struct ibm_pa_feature {
{ .pabyte = 1, .pabit = 1, .invert = 1, .cpu_features = CPU_FTR_NODSISRALIGN },
{ .pabyte = 5, .pabit = 0, .cpu_features = CPU_FTR_REAL_LE,
.cpu_user_ftrs = PPC_FEATURE_TRUE_LE },
+ { .pabyte = 24, .pabit = 0, .cpu_features = CPU_FTR_LARGE_DEC },
/*
* If the kernel doesn't support TM (ie CONFIG_PPC_TRANSACTIONAL_MEM=n),
* we don't want to turn on TM here, so we use the *_COMP versions
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 2b33cfa..5d13f06 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -946,10 +946,7 @@ static void register_decrementer_clockevent(int cpu)
static void enable_large_decrementer(void)
{
- if (!cpu_has_feature(CPU_FTR_ARCH_300))
- return;
-
- if (decrementer_max <= DECREMENTER_DEFAULT_MAX)
+ if (!cpu_has_feature(CPU_FTR_LARGE_DEC))
return;
/*
@@ -966,7 +963,7 @@ static void __init set_decrementer_max(void)
u32 bits = 32;
/* Prior to ISAv3 the decrementer is always 32 bit */
- if (!cpu_has_feature(CPU_FTR_ARCH_300))
+ if (!cpu_has_feature(CPU_FTR_LARGE_DEC))
return;
cpu = of_find_node_by_type(NULL, "cpu");
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 0fdc4a2..6e1d75f 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -124,7 +124,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
mfspr r8,SPRN_DEC
mftb r7
mtspr SPRN_HDEC,r8
+BEGIN_FTR_SECTION
extsw r8,r8
+END_FTR_SECTION_IFCLR(CPU_FTR_LARGE_DEC)
add r8,r8,r7
std r8,HSTATE_DECEXP(r13)
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bdb3f76..bcb5401 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -214,6 +214,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
kvmppc_primary_no_guest:
/* We handle this much like a ceded vcpu */
/* put the HDEC into the DEC, since HDEC interrupts don't wake us */
+ /* HDEC may be larger than DEC for arch >= v3.00, but since the */
+ /* HDEC value came from DEC in the first place, it will fit */
mfspr r3, SPRN_HDEC
mtspr SPRN_DEC, r3
/*
@@ -295,8 +297,11 @@ kvm_novcpu_wakeup:
/* See if our timeslice has expired (HDEC is negative) */
mfspr r0, SPRN_HDEC
+BEGIN_FTR_SECTION
+ extsw r0, r0
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
li r12, BOOK3S_INTERRUPT_HV_DECREMENTER
- cmpwi r0, 0
+ cmpdi r0, 0
blt kvm_novcpu_exit
/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
@@ -390,8 +395,8 @@ kvm_secondary_got_guest:
lbz r4, HSTATE_PTID(r13)
cmpwi r4, 0
bne 63f
- lis r6, 0x7fff
- ori r6, r6, 0xffff
+ LOAD_REG_ADDR(r6, decrementer_max)
+ ld r6, 0(r6)
mtspr SPRN_HDEC, r6
/* and set per-LPAR registers, if doing dynamic micro-threading */
ld r6, HSTATE_SPLIT_MODE(r13)
@@ -968,7 +973,10 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
/* Check if HDEC expires soon */
mfspr r3, SPRN_HDEC
- cmpwi r3, 512 /* 1 microsecond */
+BEGIN_FTR_SECTION
+ extsw r3, r3
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+ cmpdi r3, 512 /* 1 microsecond */
blt hdec_soon
#ifdef CONFIG_KVM_XICS
@@ -2366,12 +2374,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
mfspr r3, SPRN_DEC
mfspr r4, SPRN_HDEC
mftb r5
- cmpw r3, r4
+ extsw r3, r3
+BEGIN_FTR_SECTION
+ extsw r4, r4
+END_FTR_SECTION_IFSET(CPU_FTR_LARGE_DEC)
+ cmpd r3, r4
ble 67f
mtspr SPRN_DEC, r4
67:
/* save expiry time of guest decrementer */
- extsw r3, r3
add r3, r3, r5
ld r4, HSTATE_KVM_VCPU(r13)
ld r5, HSTATE_KVM_VCORE(r13)
--
2.7.4
